Hi
I'm Vira. I'm a beginner in SAS. I want to perform data analysis of my research in SAS 9.0.
Firstly, let me briefly describe about my experimental design. The experiment laid out on split-plot design with four replications:
1. The experiment consists of two rice cultivation methods, conventional tillage (CT) compared with no-till system (NT)
2. The experiment designed to test on four rice growing sequences (RS): RS1: 1 rice/year, RS2: 2 rice/year ( 1st rice sown in April and harvested in early July. 2nd rice sown at the end of July and harvested in November) RS3: 2 rice/year (1st rice sown in July and harvested in November. 2nd rice sown in December and harvested in the March of the following year), and RS4: 3 rice/year.
3. Three levels of fertilization were applied to each treatment: low (F0), medium (F1), and high (F2).
4. I obtained soil samples from four depths of soil layer (cm): D1 (0-5), D2 (5-10), D3 (10-20), and D4 (20-40).
In summary, there are four factors and four replications in my experiment:
1. Tow cultivation method: CT & NT
2. Four rice growing sequences: RS1, RS2, RS3, and RS4
3. Three levels of fertilization: F0, F1, and F2
4. Four depths of soil layer: D1, D2, D3, and D4.
I'd like to be recommended the most appropriated procedure in SAS to perform the data analysis in my research, and its procedure.
I'm waiting to hearing from all of you.
Thanks in advace for advice!
With regards,
Vira168
Do whatever you can to get a copy of SAS for Mixed Models, 2nd ed., by Littell et al. It has lots of code for split-split plot models.
Assuming the response is yield (MT/ha or something similar), then PROC MIXED is almost certainly where you want to go. Some of your factors are internally correlated (soil depth) in a spatial sense, while the others are each a successive split of the plots.
I am thinking of something like:
proc mixed;
class cult_method seq fert depth rep;
model yield =cult_method|seq|fert|depth;
random intercept/subject=rep;
/* very simple at first, but should probably include at least first order interactions as well */
lsmeans cult_method|seq|fert|depth/diff adjust=simulate(seed=1) adjdfe=row;
run;
Steve Denham
Are you ready for the spotlight? We're accepting content ideas for SAS Innovate 2025 to be held May 6-9 in Orlando, FL. The call is open until September 25. Read more here about why you should contribute and what is in it for you!
ANOVA, or Analysis Of Variance, is used to compare the averages or means of two or more populations to better understand how they differ. Watch this tutorial for more.
Find more tutorials on the SAS Users YouTube channel.